Is Pre-training Applicable to the Decoder for Dense Prediction?

• URL: http://arxiv.org/abs/2503.07637v2
• Date: Sat, 15 Mar 2025 16:38:39 GMT
• Title: Is Pre-training Applicable to the Decoder for Dense Prediction?
• Authors: Chao Ning, Wanshui Gan, Weihao Xuan, Naoto Yokoya,
• Abstract summary: We introduce $times$Net, which facilitates a "pre-trained encoder $times$ pre-trained decoder" collaboration through three innovative designs.<n>By simply coupling the pre-trained encoder and pre-trained decoder, $times$Net distinguishes itself as a highly promising approach.<n>Despite its streamlined design, $times$Net outperforms advanced methods in tasks such as monocular depth estimation and semantic segmentation.
• Score: 13.542355644833544
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Pre-trained encoders are widely employed in dense prediction tasks for their capability to effectively extract visual features from images. The decoder subsequently processes these features to generate pixel-level predictions. However, due to structural differences and variations in input data, only encoders benefit from pre-learned representations from vision benchmarks such as image classification and self-supervised learning, while decoders are typically trained from scratch. In this paper, we introduce $\times$Net, which facilitates a "pre-trained encoder $\times$ pre-trained decoder" collaboration through three innovative designs. $\times$Net enables the direct utilization of pre-trained models within the decoder, integrating pre-learned representations into the decoding process to enhance performance in dense prediction tasks. By simply coupling the pre-trained encoder and pre-trained decoder, $\times$Net distinguishes itself as a highly promising approach. Remarkably, it achieves this without relying on decoding-specific structures or task-specific algorithms. Despite its streamlined design, $\times$Net outperforms advanced methods in tasks such as monocular depth estimation and semantic segmentation, achieving state-of-the-art performance particularly in monocular depth estimation. and semantic segmentation, achieving state-of-the-art results, especially in monocular depth estimation. embedding algorithms. Despite its streamlined design, $\times$Net outperforms advanced methods in tasks such as monocular depth estimation and semantic segmentation, achieving state-of-the-art performance particularly in monocular depth estimation.

Related papers

• Should we pre-train a decoder in contrastive learning for dense prediction tasks? [0.7237068561453082]
  We propose a framework-agnostic adaptation to convert an encoder-only self-supervised learning (SSL) contrastive approach to an efficient encoder-decoder framework. We first update the existing architecture to accommodate a decoder and its respective contrastive loss. We then introduce a weighted encoder-decoder contrastive loss with non-competing objectives that facilitates the joint encoder-decoder architecture pre-training.
  arXiv  Detail & Related papers  (2025-03-21T20:19:13Z)
• Enhancing Hyperspectral Image Prediction with Contrastive Learning in Low-Label Regime [0.810304644344495]
  Self-supervised contrastive learning is an effective approach for addressing the challenge of limited labelled data. We evaluate the method's performance for both the single-label and multi-label classification tasks.
  arXiv  Detail & Related papers  (2024-10-10T10:20:16Z)
• CLIP Can Understand Depth [5.6138460823631835]
  We adapt CLIP for meaningful quality of monocular depth estimation with dense prediction. Our model exhibits impressive performance matching several previous state-of-the-art vision-only models.
  arXiv  Detail & Related papers  (2024-02-05T18:09:33Z)
• Regress Before Construct: Regress Autoencoder for Point Cloud Self-supervised Learning [18.10704604275133]
  Masked Autoencoders (MAE) have demonstrated promising performance in self-supervised learning for 2D and 3D computer vision. We propose Point Regress AutoEncoder (Point-RAE), a new scheme for regressive autoencoders for point cloud self-supervised learning. Our approach is efficient during pre-training and generalizes well on various downstream tasks.
  arXiv  Detail & Related papers  (2023-09-25T17:23:33Z)
• SemHint-MD: Learning from Noisy Semantic Labels for Self-Supervised Monocular Depth Estimation [19.229255297016635]
  Self-supervised depth estimation can be trapped in a local minimum due to the gradient-locality issue of the photometric loss. We present a framework to enhance depth by leveraging semantic segmentation to guide the network to jump out of the local minimum.
  arXiv  Detail & Related papers  (2023-03-31T17:20:27Z)
• ALSO: Automotive Lidar Self-supervision by Occupancy estimation [70.70557577874155]
  We propose a new self-supervised method for pre-training the backbone of deep perception models operating on point clouds. The core idea is to train the model on a pretext task which is the reconstruction of the surface on which the 3D points are sampled. The intuition is that if the network is able to reconstruct the scene surface, given only sparse input points, then it probably also captures some fragments of semantic information.
  arXiv  Detail & Related papers  (2022-12-12T13:10:19Z)
• Learning Invariant World State Representations with Predictive Coding [1.8963850600275547]
  We develop a new predictive coding-based architecture and a hybrid fully-supervised/self-supervised learning method. We evaluate the robustness of our model on a new synthetic dataset.
  arXiv  Detail & Related papers  (2022-07-06T21:08:30Z)
• X-Distill: Improving Self-Supervised Monocular Depth via Cross-Task Distillation [69.9604394044652]
  We propose a novel method to improve the self-supervised training of monocular depth via cross-task knowledge distillation. During training, we utilize a pretrained semantic segmentation teacher network and transfer its semantic knowledge to the depth network. We extensively evaluate the efficacy of our proposed approach on the KITTI benchmark and compare it with the latest state of the art.
  arXiv  Detail & Related papers  (2021-10-24T19:47:14Z)
• Dynamic Neural Representational Decoders for High-Resolution Semantic Segmentation [98.05643473345474]
  We propose a novel decoder, termed dynamic neural representational decoder (NRD) As each location on the encoder's output corresponds to a local patch of the semantic labels, in this work, we represent these local patches of labels with compact neural networks. This neural representation enables our decoder to leverage the smoothness prior in the semantic label space, and thus makes our decoder more efficient.
  arXiv  Detail & Related papers  (2021-07-30T04:50:56Z)
• Self-Supervision by Prediction for Object Discovery in Videos [62.87145010885044]
  In this paper, we use the prediction task as self-supervision and build a novel object-centric model for image sequence representation. Our framework can be trained without the help of any manual annotation or pretrained network. Initial experiments confirm that the proposed pipeline is a promising step towards object-centric video prediction.
  arXiv  Detail & Related papers  (2021-03-09T19:14:33Z)
• Cross-Thought for Sentence Encoder Pre-training [89.32270059777025]
  Cross-Thought is a novel approach to pre-training sequence encoder. We train a Transformer-based sequence encoder over a large set of short sequences. Experiments on question answering and textual entailment tasks demonstrate that our pre-trained encoder can outperform state-of-the-art encoders.
  arXiv  Detail & Related papers  (2020-10-07T21:02:41Z)
• Representation Learning for Sequence Data with Deep Autoencoding Predictive Components [96.42805872177067]
  We propose a self-supervised representation learning method for sequence data, based on the intuition that useful representations of sequence data should exhibit a simple structure in the latent space. We encourage this latent structure by maximizing an estimate of predictive information of latent feature sequences, which is the mutual information between past and future windows at each time step. We demonstrate that our method recovers the latent space of noisy dynamical systems, extracts predictive features for forecasting tasks, and improves automatic speech recognition when used to pretrain the encoder on large amounts of unlabeled data.
  arXiv  Detail & Related papers  (2020-10-07T03:34:01Z)

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.