Adaptive Signal Resuscitation: Channel-wise Post-Pruning Repair for Sparse Vision Networks

• URL: http://arxiv.org/abs/2605.21426v1
• Date: Wed, 20 May 2026 17:19:01 GMT
• Title: Adaptive Signal Resuscitation: Channel-wise Post-Pruning Repair for Sparse Vision Networks
• Abstract summary: One-shot magnitude pruning can cause severe accuracy collapse in the high-sparsity regime.<n>We propose Adaptive Signal Resuscitation (ASR) as a training-free channel-wise repair method.<n>ASR estimates a variance-matching correction for each output channel and stabilizes it with a data-driven shrinkage rule.
• Score: 8.5133415329194
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: One-shot magnitude pruning can cause severe accuracy collapse in the high-sparsity regime, even when the pruning mask preserves the largest weights. We argue that this failure reflects a granularity mismatch in post-pruning repair. Under global magnitude pruning, nearly collapsed channels can coexist with channels that retain informative activation variance within the same layer. Existing layer-wise activation repair methods apply a single correction to the whole layer, and can therefore over-amplify damaged channels while trying to restore the layer-level signal. We propose Adaptive Signal Resuscitation (ASR), a training-free channel-wise repair method that matches the granularity of repair to the granularity of damage. ASR estimates a variance-matching correction for each output channel and stabilizes it with a data-driven shrinkage rule, suppressing unreliable corrections for channels with weak post-pruning signal while preserving corrections for healthier channels. Applied before BatchNorm recalibration, ASR requires only forward passes on a small calibration set and no retraining. Across three datasets, four convolutional architectures, and both unstructured and structured sparsity settings, ASR generally improves over layer-wise repair, with the clearest gains in high-sparsity regimes. On ResNet-50 at 90% sparsity, ASR recovers 55.6% top-1 accuracy on CIFAR-10, compared with 41.0% for layer-wise repair and 28.0% for BatchNorm-only recalibration. Ablations show that naive channel-wise variance matching is insufficient, and that shrinkage stabilizes post-pruning repair.

Related papers

• LoRA-RC: Reservoir Computing with Low-Rank Adaptation [0.0]
  LoRA-RC adapts the recurrent matrix through a low-rank correction driven by streaming prediction errors.<n>On a Lorenz system with an abrupt parameter drift, LoRA-RC cuts post-drift prediction error by 56% versus a fixed RC and 51% versus readout-only adaptation.
  arXiv  Detail & Related papers  (2026-09-11T01:19:48Z)
• Universal recovery in approximate quantum error correction [53.73800998389749]
  Universal recovery is the existence of a single recovery map that corrects an entire family of error channels.<n>In exact quantum error correction, linearity guarantees that a code correcting a given error set also corrects every channel whose Kraus operators lie in its linear span.<n>We show that a single recovery map can simultaneously correct every channel controlled by a given error set.
  arXiv  Detail & Related papers  (2026-08-29T00:25:52Z)
• SHIFT-LLM: Distribution Shift Correction in Depth-Pruned LLMs [18.494055578192015]
  We introduce SHIFT-LLM, a training-free post-pruning correction framework that inserts a Linear Residual Adapter at each pruning site.<n>Each LRA preserves the identity pathway of the original residual block and adds a lightweight affine residual correction.<n>Experiments on five model families, six layer-selection criteria, and seven zero-shot benchmarks show that SHIFT-LLM consistently recovers accuracy lost to depth pruning.
  arXiv  Detail & Related papers  (2026-08-25T19:01:58Z)
• Bend the Basics: Degradation-Aware Deformable Tokenization for All-in-One Image Restoration [72.64498743287601]
  All-in-one image restoration seeks a single model that can recover images degraded by diverse and spatially non-uniform corruptions.<n>We present Flexible Image Transformer (FIT) that explicitly models degradation awareness across the entire pipeline.<n>FIT achieves state-of-the-art performance with 30.72 dB average PSNR on the five-degradation setting and 32.83 dB on the three-degradation setting, outperforming recent unified restoration methods by +0.5$sim$1.1 dB.
  arXiv  Detail & Related papers  (2026-08-07T05:44:31Z)
• HARP: Hadamard-Preconditioned Adaptive Rotation Processor for Extreme LLM Quantization [48.87937677659571]
  We introduce HARP (Hadamard-preconditioned Adaptive Rotation Processor), a learnable structured two-sided processor that replaces fixed Hadamard mixing.<n>Across 2-4 bit settings on models ranging from 1B to 70B parameters, HARP improves perplexity and zero-shot accuracy over fixed RHT.<n>HarP preserves deployment efficiency, reaching 128 tok/s versus 61 tok/s for FP16.
  arXiv  Detail & Related papers  (2026-05-28T12:24:15Z)
• Relative Repairability: A Calibration-Based Diagnostic for High-Sparsity Post-Pruning Allocation [12.288779306467768]
  Relative Repairability (RR) is a calibration based diagnostic that compares the raw activation distortion caused by layerwise pruning with the residual distortion left after channelwise variance matching repair.<n>RR is most useful near an architecture dependent recoverability transition, where standard structural or magnitude based allocation priors begin to lose reliability but post repair recovery has not yet fully collapsed.<n>These results suggest that high sparsity pruning should allocate not only retained weights, but also repairable damage.
  arXiv  Detail & Related papers  (2026-05-25T07:12:38Z)
• Clipping Bottleneck: Stabilizing RLVR via Stochastic Recovery of Near-Boundary Signals [83.0127582612634]
  Near-boundary Rescue (NSR) is a minimal, plug-and-play modification that retains out-of-bound tokens to recover lost signals.<n>NSR substantially improves training stability and delivers consistent gains over strong baselines such as DAPO and GSPO.
  arXiv  Detail & Related papers  (2026-05-21T16:45:31Z)
• How Sparsity Allocation Shapes Label-Free Post-Pruning Recoverability [4.9112670395105305]
  Post-pruning repair methods can partially recover collapsed sparse models, but their effectiveness depends on the sparse model left by the upstream pruning allocation.<n>This paper studies how sparsity allocation shapes post-repair recoverability under a fixed activation-statistic repair backend.
  arXiv  Detail & Related papers  (2026-05-21T04:03:24Z)
• MARR: Module-Adaptive Residual Reconstruction for Low-Bit Post-Training Quantization [42.904834974723535]
  We propose Module-Adaptive Residual Reconstruction (MARR)<n>MARR assigns a module-specific scaling coefficient to adaptively balance accumulated-error correction and residual-related HA bias for each module.<n>Experiments on several typical large language models (LLMs) and vision transformers (ViTs) demonstrate the effectiveness of MARR under low-bit quantization.
  arXiv  Detail & Related papers  (2026-05-18T07:51:49Z)
• Restoration-Aligned Generative Flow Models for Blind Motion Deblurring [57.425021485907756]
  We present DeFlow, a framework that resolves misalignment by reformulating the flow trajectory itself.<n>Under this formulation, the standard flow matching loss naturally takes the form of a residual loss.<n>Experiments on GoPro, HIDE, RealBlur, and RWBI demonstrate that DeFlow achieves strong restoration fidelity and perceptual realism.
  arXiv  Detail & Related papers  (2026-05-09T10:05:51Z)
• Exactness Matters for Physical Rule Enforcement [4.230349220081444]
  It remains unclear when stronger physical rule enforcement becomes reliable and when it becomes a source of distribution shift.<n>We study this question through operator exactness, meaning whether the repair map is the identity on the target manifold.<n> Controlled mismatch, screened cleanup, adaptive gating, and external-backbone checks show that the best approximate-regime operating point can be raw or near-identity.
  arXiv  Detail & Related papers  (2026-05-08T07:59:59Z)
• Stream-R1: Reliability-Perplexity Aware Reward Distillation for Streaming Video Generation [52.10062792673558]
  Distillation-based acceleration has become foundational for making autore streaming video diffusion models practical.<n>Existing methods treat every rollout, frame, and pixel as equally reliable supervision.<n>We propose Stream-R1, a Reliability-Perplexity Aware Reward Distillation framework.
  arXiv  Detail & Related papers  (2026-05-05T15:15:30Z)
• Diffusion Controller: Framework, Algorithms and Parameterization [54.82539154511621]
  We present a unified control-theoretic view that casts reverse diffusion sampling as state-only control within (generalized) linearly-solvable Markov Decision Processes.<n>Under this framework, control acts by reweighting the pretrained reverse-time transition kernels, balancing terminal objectives against an $f$-divergence cost.<n>Experiments on Stable Diffusion v1.4 show consistent gains in preference-alignment win rates and improved quality-efficiency trade-offs.
  arXiv  Detail & Related papers  (2026-03-07T01:49:59Z)
• Spectral Complex Autoencoder Pruning: A Fidelity-Guided Criterion for Extreme Structured Channel Compression [7.913101398893967]
  We propose a reconstruction-based criterion that measures functional redundancy at the level of individual output channels.<n>We transform a complex interaction field to the frequency domain and train a low-capacity autoencoder to reconstruct normalized spectra.<n>We find that spectral reconstruction fidelity of complex interaction fields is an effective proxy for channel-level redundancy under aggressive compression.
  arXiv  Detail & Related papers  (2026-01-14T10:34:18Z)
• CARE What Fails: Contrastive Anchored-REflection for Verifiable Multimodal [84.71254539482369]
  Group-relative reinforcement learning with verifiable rewards (RLVR) often wastes the most informative data it already has the failures.<n>We present CARE, a failure-centric post-training framework for multimodal reasoning that turns errors into supervision.<n> CARE improves accuracy and training smoothness while explicitly increasing the share of learning signal that comes from failures.
  arXiv  Detail & Related papers  (2025-12-22T16:34:21Z)
• HSCP: A Two-Stage Spectral Clustering Framework for Resource-Constrained UAV Identification [16.880773405024126]
  This paper introduces HSCP, a Hierarchical Spectral Clustering Pruning framework.<n>It combines layer pruning with channel pruning to achieve extreme compression, high performance, and efficient inference.<n>Experiments on the UAV-M100 benchmark demonstrate that HSCP outperforms existing channel and layer pruning methods.
  arXiv  Detail & Related papers  (2025-12-05T16:03:53Z)
• SecDiff: Diffusion-Aided Secure Deep Joint Source-Channel Coding Against Adversarial Attacks [73.41290017870097]
  SecDiff is a plug-and-play, diffusion-aided decoding framework.<n>It significantly enhances the security and robustness of deep J SCC under adversarial wireless environments.
  arXiv  Detail & Related papers  (2025-11-03T11:24:06Z)
• WACA-UNet: Weakness-Aware Channel Attention for Static IR Drop Prediction in Integrated Circuit Design [22.68767218144094]
  Traditional simulation-based solvers are computationally expensive and difficult to scale.<n>We address this challenge by reformulating IR drop estimation as a pixel-wise regression task on heterogeneous multi-channel physical maps.
  arXiv  Detail & Related papers  (2025-07-25T12:07:16Z)
• CATRO: Channel Pruning via Class-Aware Trace Ratio Optimization [61.71504948770445]
  We propose a novel channel pruning method via Class-Aware Trace Ratio Optimization (CATRO) to reduce the computational burden and accelerate the model inference. We show that CATRO achieves higher accuracy with similar cost or lower cost with similar accuracy than other state-of-the-art channel pruning algorithms. Because of its class-aware property, CATRO is suitable to prune efficient networks adaptively for various classification subtasks, enhancing handy deployment and usage of deep networks in real-world applications.
  arXiv  Detail & Related papers  (2021-10-21T06:26:31Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.