Related papers: ComKD-CLIP: Comprehensive Knowledge Distillation f…
We propose a novel knowledge distillation approach, CustomKD, that effectively leverages large vision foundation models (LVFMs) to enhance the performance of edge models (e.g., MobileNetV3). Despite recent advancements in LVFMs, such as…
We study the effectiveness of data-balancing for mitigating biases in contrastive language-image pretraining (CLIP), identifying areas of strength and limitation. First, we reaffirm prior conclusions that CLIP models can inadvertently…
In this paper, we propose a novel cross-modal distillation method, called TinyCLIP, for large-scale language-image pre-trained models. The method introduces two core techniques: affinity mimicking and weight inheritance. Affinity mimicking…
The scarcity of annotated data has sparked significant interest in unsupervised pre-training methods that leverage medical reports as auxiliary signals for medical visual representation learning. However, existing research overlooks the…
Knowledge distillation (KD) has emerged as a promising technique for addressing the computational challenges associated with deploying large-scale recommender systems. KD transfers the knowledge of a massive teacher system to a compact…
The Contrastive Language-Image Pre-training (CLIP) Model is a recently proposed large-scale pre-train model which attracts increasing attention in the computer vision community. Benefiting from its gigantic image-text training set, the CLIP…
Recent developments in natural language representations have been accompanied by large and expensive models that leverage vast amounts of general-domain text through self-supervised pre-training. Due to the cost of applying such models to…
Beyond the success of Contrastive Language-Image Pre-training (CLIP), recent trends mark a shift toward exploring the applicability of lightweight vision-language models for resource-constrained scenarios. These models often deliver…
Multi-Teacher knowledge distillation provides students with additional supervision from multiple pre-trained teachers with diverse information sources. Most existing methods explore different weighting strategies to obtain a powerful…
In this paper, we investigate the knowledge distillation (KD) strategy for object detection and propose an effective framework applicable to both homogeneous and heterogeneous student-teacher pairs. The conventional feature imitation…
Data-Free Knowledge Distillation (DFKD) has shown great potential in creating a compact student model while alleviating the dependency on real training data by synthesizing surrogate data. However, prior arts are seldom discussed under…
Knowledge distillation is widely applied in various fundamental vision models to enhance the performance of compact models. Existing knowledge distillation methods focus on designing different distillation targets to acquire knowledge from…
Most knowledge distillation (KD) methodologies predominantly focus on teacher-student pairs with similar architectures, such as both being convolutional neural networks (CNNs). However, the potential and flexibility of KD can be greatly…
The Image Difference Captioning (IDC) task aims to describe the visual differences between two similar images with natural language. The major challenges of this task lie in two aspects: 1) fine-grained visual differences that require…
In this paper, we introduce DetailCLIP: A Detail-Oriented CLIP to address the limitations of contrastive learning-based vision-language models, particularly CLIP, in handling detail-oriented and fine-grained tasks like segmentation. While…
Aligning image and text encoders from scratch using contrastive learning requires large amounts of paired image-text data. We alleviate this need by aligning individually pre-trained language and vision representation models using a much…
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…
The parameter-efficient adaptation of the image-text pretraining model CLIP for video-text retrieval is a prominent area of research. While CLIP is focused on image-level vision-language matching, video-text retrieval demands comprehensive…
Knowledge distillation is considered as a training and compression strategy in which two neural networks, namely a teacher and a student, are coupled together during training. The teacher network is supposed to be a trustworthy predictor…
Federated learning is widely used to learn intelligent models from decentralized data. In federated learning, clients need to communicate their local model updates in each iteration of model learning. However, model updates are large in…