Semantic-Aware Autoregressive Image Modeling for Visual Representation Learning

• URL: http://arxiv.org/abs/2312.10457v1
• Date: Sat, 16 Dec 2023 14:03:10 GMT
• Title: Semantic-Aware Autoregressive Image Modeling for Visual Representation Learning
• Abstract summary: We present a semantic-aware autoregressive image modeling (SemAIM) method to tackle this challenge. The key insight of SemAIM is to autoregressive model images from the semantic patches to the less semantic patches. With ViT-B, SemAIM achieves 84.1% top-1 accuracy for fine-tuning on ImageNet, 51.3% AP and 45.4% AP for object detection and instance/semantic segmentation.
• Score: 9.960835000101115
• License: http://creativecommons.org/licenses/by-sa/4.0/
• Abstract: The development of autoregressive modeling (AM) in computer vision lags behind natural language processing (NLP) in self-supervised pre-training. This is mainly caused by the challenge that images are not sequential signals and lack a natural order when applying autoregressive modeling. In this study, inspired by human beings' way of grasping an image, i.e., focusing on the main object first, we present a semantic-aware autoregressive image modeling (SemAIM) method to tackle this challenge. The key insight of SemAIM is to autoregressive model images from the semantic patches to the less semantic patches. To this end, we first calculate a semantic-aware permutation of patches according to their feature similarities and then perform the autoregression procedure based on the permutation. In addition, considering that the raw pixels of patches are low-level signals and are not ideal prediction targets for learning high-level semantic representation, we also explore utilizing the patch features as the prediction targets. Extensive experiments are conducted on a broad range of downstream tasks, including image classification, object detection, and instance/semantic segmentation, to evaluate the performance of SemAIM. The results demonstrate SemAIM achieves state-of-the-art performance compared with other self-supervised methods. Specifically, with ViT-B, SemAIM achieves 84.1% top-1 accuracy for fine-tuning on ImageNet, 51.3% AP and 45.4% AP for object detection and instance segmentation on COCO, which outperforms the vanilla MAE by 0.5%, 1.0%, and 0.5%, respectively.

Related papers

• GIFT: Goal-Injected Fine-Tuning for Efficient Manipulation Policy Adaptation [24.751598161321933]
  Goal-Injected Fine-Tuning (GIFT) is a lightweight and efficient fine-tuning framework that seamlessly integrates generated goal images into pretrained VLA models.<n>Our approach introduces goal image features into observations via a zero-d convolution which progressively grows parameters from zero.<n>As training proceeds, goal information is gradually incorporated, enabling efficient goal understanding without disrupting model stability.
  arXiv  Detail & Related papers  (2026-09-07T03:56:49Z)
• AIM-Bench: Benchmarking and Improving Affective Image Manipulation via Fine-Grained Hierarchical Control [30.172679310027533]
  Affective Image Manipulation (AIM) aims to evoke specific emotions through targeted editing.<n>We introduce the first benchmark designed for AIM termed AIM-Bench.<n>This benchmark is built upon a dual-path affective modeling scheme that integrates the Mikels emotion taxonomy with the Valence-Arousal-Dominance framework.
  arXiv  Detail & Related papers  (2026-04-12T04:32:30Z)
• Suppressing Non-Semantic Noise in Masked Image Modeling Representations [10.470642234528988]
  Masked Image Modeling (MIM) has become a ubiquitous self-supervised vision paradigm.<n>We show that MIM objectives cause the learned representations to retain non-semantic information.<n>We propose a simple method, Semantically Orthogonal Artifact Projection (SOAP), to directly suppress non-semantic information in patch representations.
  arXiv  Detail & Related papers  (2026-03-31T19:22:21Z)
• Next-Embedding Prediction Makes Strong Vision Learners [68.55755328850634]
  We train models to generate embeddings to perform predictive tasks directly.<n>Next-Embedding Predictive Autoregression (NEPA) achieves strong results across tasks.<n>We believe generative pretraining from embeddings provides a simple, scalable, and potentially modality-agnostic alternative to visual self-supervised learning.
  arXiv  Detail & Related papers  (2025-12-18T18:59:58Z)
• Training-free Detection of AI-generated images via Cropping Robustness [33.85512004342153]
  WaRPAD is a training-free AI-generated image detection algorithm based on self-supervised models.<n>We show that WaRPAD consistently achieves competitive performance and demonstrates strong robustness to test-time corruptions.
  arXiv  Detail & Related papers  (2025-11-18T01:21:47Z)
• IteRPrimE: Zero-shot Referring Image Segmentation with Iterative Grad-CAM Refinement and Primary Word Emphasis [46.502962768034166]
  Zero-shot Referring Image identifies the instance mask that best aligns with a referring expression without training and fine-tuning. Previous CLIP-based models exhibit a notable reduction in their capacity to discern relative spatial relationships of objects. IteRPrimE outperforms previous state-of-the-art zero-shot methods, particularly excelling in out-of-domain scenarios.
  arXiv  Detail & Related papers  (2025-03-02T15:19:37Z)
• VQAttack: Transferable Adversarial Attacks on Visual Question Answering via Pre-trained Models [58.21452697997078]
  We propose a novel VQAttack model, which can generate both image and text perturbations with the designed modules. Experimental results on two VQA datasets with five validated models demonstrate the effectiveness of the proposed VQAttack.
  arXiv  Detail & Related papers  (2024-02-16T21:17:42Z)
• On quantifying and improving realism of images generated with diffusion [50.37578424163951]
  We propose a metric, called Image Realism Score (IRS), computed from five statistical measures of a given image. IRS is easily usable as a measure to classify a given image as real or fake. We experimentally establish the model- and data-agnostic nature of the proposed IRS by successfully detecting fake images generated by Stable Diffusion Model (SDM), Dalle2, Midjourney and BigGAN. Our efforts have also led to Gen-100 dataset, which provides 1,000 samples for 100 classes generated by four high-quality models.
  arXiv  Detail & Related papers  (2023-09-26T08:32:55Z)
• Learning from History: Task-agnostic Model Contrastive Learning for Image Restoration [79.04007257606862]
  This paper introduces an innovative method termed 'learning from history', which dynamically generates negative samples from the target model itself. Our approach, named Model Contrastive Learning for Image Restoration (MCLIR), rejuvenates latency models as negative models, making it compatible with diverse image restoration tasks.
  arXiv  Detail & Related papers  (2023-09-12T07:50:54Z)
• Efficient Masked Autoencoders with Self-Consistency [34.7076436760695]
  Masked image modeling (MIM) has been recognized as a strong self-supervised pre-training method in computer vision. We propose efficient masked autoencoders with self-consistency (EMAE) to improve the pre-training efficiency. EMAE consistently obtains state-of-the-art transfer ability on a variety of downstream tasks, such as image classification, object detection, and semantic segmentation.
  arXiv  Detail & Related papers  (2023-02-28T09:21:12Z)
• Exploring Stochastic Autoregressive Image Modeling for Visual Representation [24.582376834198403]
  We propose a novel autoregressive image modeling (named SAIM) by the two simple designs. By introducing prediction and the parallel encoder-decoder, SAIM significantly improve the performance of autoregressive image modeling. Our method achieves the best accuracy (83.9%) on the vanilla ViT-Base model among methods using only ImageNet-1K data.
  arXiv  Detail & Related papers  (2022-12-03T13:04:29Z)
• BEiT v2: Masked Image Modeling with Vector-Quantized Visual Tokenizers [117.79456335844439]
  We propose to use a semantic-rich visual tokenizer as the reconstruction target for masked prediction. We then pretrain vision Transformers by predicting the original visual tokens for the masked image patches. Experiments on image classification and semantic segmentation show that our approach outperforms all compared MIM methods.
  arXiv  Detail & Related papers  (2022-08-12T16:48:10Z)
• Contrastive Learning Rivals Masked Image Modeling in Fine-tuning via Feature Distillation [42.37533586611174]
  Masked image modeling (MIM) learns representations with remarkably good fine-tuning performances. In this paper, we show that the inferior fine-tuning performance of pre-training approaches can be significantly improved by a simple post-processing.
  arXiv  Detail & Related papers  (2022-05-27T17:59:36Z)
• Group-Wise Semantic Mining for Weakly Supervised Semantic Segmentation [49.90178055521207]
  This work addresses weakly supervised semantic segmentation (WSSS), with the goal of bridging the gap between image-level annotations and pixel-level segmentation. We formulate WSSS as a novel group-wise learning task that explicitly models semantic dependencies in a group of images to estimate more reliable pseudo ground-truths. In particular, we devise a graph neural network (GNN) for group-wise semantic mining, wherein input images are represented as graph nodes.
  arXiv  Detail & Related papers  (2020-12-09T12:40:13Z)
• Dense Contrastive Learning for Self-Supervised Visual Pre-Training [102.15325936477362]
  We present dense contrastive learning, which implements self-supervised learning by optimizing a pairwise contrastive (dis)similarity loss at the pixel level between two views of input images. Compared to the baseline method MoCo-v2, our method introduces negligible computation overhead (only 1% slower)
  arXiv  Detail & Related papers  (2020-11-18T08:42:32Z)

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.