Related papers: ALADIN:Attribute-Language Distillation Network for…

Low-resolution face recognition is a challenging task due to the missing of informative details. Recent approaches based on knowledge distillation have proven that high-resolution clues can well guide low-resolution face recognition via…

Significant progress has been achieved on the improvement and downstream usages of the Contrastive Language-Image Pre-training (CLIP) vision-language model, while less attention is paid to the interpretation of CLIP. We propose a…

Knowledge distillation (KD) is a key technique for compressing large-scale language models (LLMs), yet prevailing logit-based methods typically employ static strategies that are misaligned with the dynamic learning process of student…

Generative recommendation models employing Semantic IDs (SIDs) exhibit strong potential, yet their practical deployment is bottlenecked by the high inference latency of beam-expanded autoregressive decoding. In this work, we identify that…

Label assignment in object detection aims to assign targets, foreground or background, to sampled regions in an image. Unlike labeling for image classification, this problem is not well defined due to the object's bounding box. In this…

Cross-Domain Few-Shot Learning (CDFSL) adapts models trained with large-scale general data (source domain) to downstream target domains with only scarce training data, where the research on vision-language models (e.g., CLIP) is still in…

Vision-language models (VLMs) have demonstrated exceptional generalization capabilities for downstream tasks. Due to its efficiency, prompt learning has gradually become a more effective and efficient method for transferring VLMs to…

Text--image retrieval is necessary for applications such as product recommendation. Embedding-based approaches like CLIP enable efficient large-scale retrieval via vector similarity search, but they are primarily trained on literal…

Pre-trained Vision-Language (V-L) models set the benchmark for generalization to downstream tasks among the noteworthy contenders. Many characteristics of the V-L model have been explored in existing research including the challenge of the…

Deep learning models have achieved significant results across various computer vision tasks. However, due to the large number of parameters in these models, deploying them in real-time scenarios is a critical challenge, specifically in…

Recently, CLIP has become an important model for aligning images and text in multi-modal contexts. However, researchers have identified limitations in the ability of CLIP's text and image encoders to extract detailed knowledge from pairs of…

This paper investigates algorithms for solving distributed consensus optimization problems that are non-convex. Since Typical ALADIN (Typical Augmented Lagrangian based Alternating Direction Inexact Newton Method, T-ALADIN for short) [1] is…

Few-shot Test-Time Domain Adaptation focuses on adapting a model at test time to a specific domain using only a few unlabeled examples, addressing domain shift. Prior methods leverage CLIP's strong out-of-distribution (OOD) abilities by…

We demonstrate that in knowledge distillation for diffusion models, the teacher network's highly complex denoising process - stemming from its substantially larger capacity - poses a significant challenge for the student model to faithfully…

Contrastive Language-Image Pre-training (CLIP) has been a celebrated method for training vision encoders to generate image/text representations facilitating various applications. Recently, CLIP has been widely adopted as the vision backbone…

Masked image modeling (MIM) is a highly effective self-supervised learning (SSL) approach to extract useful feature representations from unannotated data. Predominantly used random masking methods make SSL less effective for medical images…

We propose a local adversarial disentangling network (LADN) for facial makeup and de-makeup. Central to our method are multiple and overlapping local adversarial discriminators in a content-style disentangling network for achieving local…

Vision-Language Navigation (VLN) is a challenging task that requires an embodied agent to perform action-level modality alignment, i.e., make instruction-asked actions sequentially in complex visual environments. Most existing VLN agents…

While large vision-language models (VLMs) demonstrate strong long-context understanding, their prevalent small branches fail on linguistics-photography alignment for a limited window size. We discover that knowledge distillation improves…

Self-distillation enables language models to learn on-policy from their own trajectories by using the same model as both student and teacher, with the teacher being conditioned on privileged information unavailable to the student. Such…