相关论文: Dyn-Adapter: Towards Disentangled Representation f…

As neural networks are increasingly being applied to real-world applications, mechanisms to address distributional shift and sequential task learning without forgetting are critical. Methods incorporating network expansion have shown…

We revisit continual learning~(CL), which enables pre-trained vision transformers (ViTs) to sequentially fine-tune on new downstream tasks over time. However, as the scale of these models increases, catastrophic forgetting remains a more…

The speed-precision trade-off is a critical problem for visual object tracking which usually requires low latency and deployment on constrained resources. Existing solutions for efficient tracking mainly focus on adopting light-weight…

This paper proposes a novel approach to address the challenge that pretrained VLA models often fail to effectively improve performance and reduce adaptation costs during standard supervised finetuning (SFT). Some advanced finetuning methods…

Line segment detection is a fundamental low-level task in computer vision, and improvements in this task can impact more advanced methods that depend on it. Most new methods developed for line segment detection are based on Convolutional…

Disentangled representation learning strives to extract the intrinsic factors within observed data. Factorizing these representations in an unsupervised manner is notably challenging and usually requires tailored loss functions or specific…

Multi-modal learning, which focuses on utilizing various modalities to improve the performance of a model, is widely used in video recognition. While traditional multi-modal learning offers excellent recognition results, its computational…

The dominant multi-camera 3D detection paradigm is based on explicit 3D feature construction, which requires complicated indexing of local image-view features via 3D-to-2D projection. Other methods implicitly introduce geometric positional…

Vision Transformer (ViT) architectures are becoming increasingly popular and widely employed to tackle computer vision applications. Their main feature is the capacity to extract global information through the self-attention mechanism,…

Image aesthetic evaluation has attracted much attention in recent years. Image aesthetic evaluation methods heavily depend on the effective aesthetic feature. Traditional meth-ods always extract hand-crafted features. However, these…

We introduce the BIR-Adapter, a parameter-efficient diffusion adapter for blind image restoration. Diffusion-based restoration methods have demonstrated promising performance in addressing this fundamental problem in computer vision,…

Recently, Transformers have gained significant popularity in image restoration tasks such as image super-resolution and denoising, owing to their superior performance. However, balancing performance and computational burden remains a…

Continual learning allows the system to learn and adapt to new tasks while retaining the knowledge acquired from previous tasks. However, deep learning models suffer from catastrophic forgetting of knowledge learned from earlier tasks while…

Pre-trained vision-language models (VLMs) have shown impressive performance on various downstream tasks by utilizing knowledge learned from large data. In general, the performance of VLMs on target tasks can be further improved by prompt…

Human Pose (HP) estimation is actively researched because of its wide range of applications. However, even estimators pre-trained on large datasets may not perform satisfactorily due to a domain gap between the training and test data. To…

Pre-trained vision-language models are able to interpret visual concepts and language semantics. Prompt learning, a method of constructing prompts for text encoders or image encoders, elicits the potentials of pre-trained models and readily…

Following language instructions to navigate in unseen environments is a challenging task for autonomous embodied agents. With strong representation capabilities, pretrained vision-and-language models are widely used in VLN. However, most of…

Inspired by the in-context learning mechanism of large language models (LLMs), a new paradigm of generalizable visual prompt-based image editing is emerging. Existing single-reference methods typically focus on style or appearance…

One key challenge of exemplar-guided image generation lies in establishing fine-grained correspondences between input and guided images. Prior approaches, despite the promising results, have relied on either estimating dense attention to…

Recent progress in deterministic prompt learning has become a promising alternative to various downstream vision tasks, enabling models to learn powerful visual representations with the help of pre-trained vision-language models. However,…