相关论文: 5%>100%: Breaking Performance Shackles of Full Fin…

Pre-training & fine-tuning can enhance the transferring efficiency and performance in visual tasks. Recent delta-tuning methods provide more options for visual classification tasks. Despite their success, existing visual delta-tuning art…

Deploying vision foundation models typically relies on efficient adaptation strategies, whereas conventional full fine-tuning suffers from prohibitive costs and low efficiency. While delta-tuning has proven effective in boosting the…

Pre-trained vision language models have shown remarkable performance on visual recognition tasks, but they typically assume the availability of complete multimodal inputs during both training and inference. In real-world scenarios, however,…

With the rapid growth in the scale of pre-trained foundation models, parameter-efficient fine-tuning techniques have gained significant attention, among which Adapter Tuning is the most widely used. Despite achieving efficiency, it still…

Recently, Multimodal Large Language Models (MLLMs) have demonstrated impressive performance on instruction-following tasks by integrating pretrained visual encoders with large language models (LLMs). However, existing approaches often…

Despite the success of transformers on various computer vision tasks, they suffer from excessive memory and computational cost. Some works present dynamic vision transformers to accelerate inference by pruning redundant tokens. A key to…

Vision-language retrieval is an important multi-modal learning topic, where the goal is to retrieve the most relevant visual candidate for a given text query. Recently, pre-trained models, e.g., CLIP, show great potential on retrieval…

Masked Autoencoders (MAE) achieve self-supervised learning of image representations by randomly removing a portion of visual tokens and reconstructing the original image as a pretext task, thereby significantly enhancing pretraining…

Aiming towards a holistic understanding of multiple downstream tasks simultaneously, there is a need for extracting features with better transferability. Though many latest self-supervised pre-training methods have achieved impressive…

The Muon optimizer has recently offered a promising alternative to AdamW for large language model training, leveraging matrix orthogonalization to produce geometry-aware updates. However, like all first-order methods, Muon can become…

Large multimodal models (LMMs) often struggle to recognize novel concepts, as they rely on pre-trained knowledge and have limited ability to capture subtle visual details. Domain-specific knowledge gaps in training also make them prone to…

Model merging offers a scalable alternative to multi-task learning but often yields suboptimal performance on classification tasks. We attribute this degradation to a geometric misalignment between the merged encoder and static…

The field of object detection and understanding is rapidly evolving, driven by advances in both traditional CNN-based models and emerging multi-modal large language models (LLMs). While CNNs like ResNet and YOLO remain highly effective for…

While multi-modal learning has advanced significantly, current approaches often treat modalities separately, creating inconsistencies in representation and reasoning. We introduce MANTA (Multi-modal Abstraction and Normalization via Textual…

Visual recognition has been dominated by convolutional neural networks (CNNs) for years. Though recently the prevailing vision transformers (ViTs) have shown great potential of self-attention based models in ImageNet classification, their…

Fine-tuning large-scale pretrained models has led to tremendous progress in well-studied modalities such as vision and NLP. However, similar gains have not been observed in many other modalities due to a lack of relevant pretrained models.…

Sub-10cm diameter nano-drones are gaining momentum thanks to their applicability in scenarios prevented to bigger flying drones, such as in narrow environments and close to humans. However, their tiny form factor also brings their major…

The presiding model generation algorithms rely on simple, inflexible adapter selection to provide personalized results. We propose the model-adapter composition problem as a generalized problem to past work factoring in practical hardware…

Adapting pre-trained representations has become the go-to recipe for learning new downstream tasks with limited examples. While literature has demonstrated great successes via representation learning, in this work, we show that substantial…

Contrastive Language-Image Pretraining (CLIP) excels at learning generalizable image representations but often falls short in zero-shot inference on certain downstream datasets. Test-time adaptation (TTA) mitigates this issue by adjusting…