TACTIC: Joint Rate-Distortion-Accuracy Optimisation for Low Bitrate Compression

• URL: http://arxiv.org/abs/2109.10658v1
• Date: Wed, 22 Sep 2021 11:27:57 GMT
• Title: TACTIC: Joint Rate-Distortion-Accuracy Optimisation for Low Bitrate Compression
• Abstract summary: TACTIC: Task-Aware Compression Through Intelligent Coding. Our lossy compression model learns based on the ratedistortion-accuracy trade-off for a specific task. Our approach is able to improve the accuracy of the ImageNet subset classification by 4.5%.
• Score: 28.88113725832339
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: We present TACTIC: Task-Aware Compression Through Intelligent Coding. Our lossy compression model learns based on the rate-distortion-accuracy trade-off for a specific task. By considering what information is important for the follow-on problem, the system trades off visual fidelity for good task performance at a low bitrate. When compared against JPEG at the same bitrate, our approach is able to improve the accuracy of ImageNet subset classification by 4.5%. We also demonstrate the applicability of our approach to other problems, providing a 3.4% accuracy and 4.9% mean IoU improvements in performance over task-agnostic compression for semantic segmentation.

Related papers

• Optimized Learned Image Compression for Facial Expression Recognition [19.83373779671629]
  This study proposes an end-to-end model designed to preserve critical features and enhance both compression and recognition performance.<n>A custom loss function is introduced to optimize the model, tailored to balance compression and recognition performance effectively.
  arXiv  Detail & Related papers  (2025-09-21T22:35:19Z)
• TACO-RL: Task Aware Prompt Compression Optimization with Reinforcement Learning [11.167198972934736]
  Large language models (LLMs) such as GPT-4 have led to a surge in the size of prompts required for optimal performance. We propose a novel and efficient reinforcement learning (RL) based task-aware prompt compression method. We demonstrate that our RL-guided compression method improves the task performance by 8% - 260% over state-of-the-art compression techniques.
  arXiv  Detail & Related papers  (2024-09-19T18:11:59Z)
• Semantic Ensemble Loss and Latent Refinement for High-Fidelity Neural Image Compression [58.618625678054826]
  This study presents an enhanced neural compression method designed for optimal visual fidelity. We have trained our model with a sophisticated semantic ensemble loss, integrating Charbonnier loss, perceptual loss, style loss, and a non-binary adversarial loss. Our empirical findings demonstrate that this approach significantly improves the statistical fidelity of neural image compression.
  arXiv  Detail & Related papers  (2024-01-25T08:11:27Z)
• Progressive Learning with Visual Prompt Tuning for Variable-Rate Image Compression [60.689646881479064]
  We propose a progressive learning paradigm for transformer-based variable-rate image compression. Inspired by visual prompt tuning, we use LPM to extract prompts for input images and hidden features at the encoder side and decoder side, respectively. Our model outperforms all current variable image methods in terms of rate-distortion performance and approaches the state-of-the-art fixed image compression methods trained from scratch.
  arXiv  Detail & Related papers  (2023-11-23T08:29:32Z)
• High-Fidelity Variable-Rate Image Compression via Invertible Activation Transformation [24.379052026260034]
  We propose the Invertible Activation Transformation (IAT) module to tackle the issue of high-fidelity fine variable-rate image compression. IAT and QLevel together give the image compression model the ability of fine variable-rate control while better maintaining the image fidelity. Our method outperforms the state-of-the-art variable-rate image compression method by a large margin, especially after multiple re-encodings.
  arXiv  Detail & Related papers  (2022-09-12T07:14:07Z)
• Recognition-Aware Learned Image Compression [0.5801044612920815]
  We propose a recognition-aware learned compression method, which optimize a rate-distortion loss alongside a task-specific loss. Our method achieves 26% higher recognition accuracy at equivalents compared to traditional methods such as BPG.
  arXiv  Detail & Related papers  (2022-02-01T03:33:51Z)
• Variable-Rate Deep Image Compression through Spatially-Adaptive Feature Transform [58.60004238261117]
  We propose a versatile deep image compression network based on Spatial Feature Transform (SFT arXiv:1804.02815) Our model covers a wide range of compression rates using a single model, which is controlled by arbitrary pixel-wise quality maps. The proposed framework allows us to perform task-aware image compressions for various tasks.
  arXiv  Detail & Related papers  (2021-08-21T17:30:06Z)
• Towards Compact CNNs via Collaborative Compression [166.86915086497433]
  We propose a Collaborative Compression scheme, which joints channel pruning and tensor decomposition to compress CNN models. We achieve 52.9% FLOPs reduction by removing 48.4% parameters on ResNet-50 with only a Top-1 accuracy drop of 0.56% on ImageNet 2012.
  arXiv  Detail & Related papers  (2021-05-24T12:07:38Z)
• Analyzing and Mitigating JPEG Compression Defects in Deep Learning [69.04777875711646]
  We present a unified study of the effects of JPEG compression on a range of common tasks and datasets. We show that there is a significant penalty on common performance metrics for high compression.
  arXiv  Detail & Related papers  (2020-11-17T20:32:57Z)
• The Rate-Distortion-Accuracy Tradeoff: JPEG Case Study [30.84385779593074]
  We focus on the design of the quantization tables in the JPEG compression standard. We offer a novel optimal tuning of these tables via continuous optimization. We report a substantial boost in performance by a simple and easily implemented modification of these tables.
  arXiv  Detail & Related papers  (2020-08-03T01:39:01Z)
• Optimizing JPEG Quantization for Classification Networks [32.20485214224392]
  We show that a simple sorted random sampling method can exceed the performance of the standard JPEG Q-table. New Q-tables can improve the compression rate by 10% to 200% when the accuracy is fixed, or improve accuracy up to $2%$ at the same compression rate.
  arXiv  Detail & Related papers  (2020-03-05T19:13:06Z)
• End-to-End Facial Deep Learning Feature Compression with Teacher-Student Enhancement [57.18801093608717]
  We propose a novel end-to-end feature compression scheme by leveraging the representation and learning capability of deep neural networks. In particular, the extracted features are compactly coded in an end-to-end manner by optimizing the rate-distortion cost. We verify the effectiveness of the proposed model with the facial feature, and experimental results reveal better compression performance in terms of rate-accuracy.
  arXiv  Detail & Related papers  (2020-02-10T10:08:44Z)

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.