Related papers: Coaching a Teachable Student
Knowledge distillation refers to the process of training a compact student network to achieve better accuracy by learning from a high capacity teacher network. Most of the existing knowledge distillation methods direct the student to follow…
Knowledge distillation is a simple but powerful way to transfer knowledge between a teacher model to a student model. Existing work suffers from at least one of the following key limitations in terms of direction and scope of transfer which…
Knowledge distillation (KD) remains challenging due to the opaque nature of the knowledge transfer process from a Teacher to a Student, making it difficult to address certain issues related to KD. To address this, we proposed UniCAM, a…
Real world deployment of multi agent reinforcement learning MARL systems is fundamentally constrained by limited compute memory and inference time. While expert policies achieve high performance they rely on costly decision cycles and large…
Motion Object Segmentation (MOS) is crucial for autonomous driving, as it enhances localization, path planning, map construction, scene flow estimation, and future state prediction. While existing methods achieve strong performance,…
End-to-end approaches to autonomous driving commonly rely on expert demonstrations. Although humans are good drivers, they are not good coaches for end-to-end algorithms that demand dense on-policy supervision. On the contrary, automated…
Neural networks can learn spurious correlations in the data, often leading to performance degradation for underrepresented subgroups. Studies have demonstrated that the disparity is amplified when knowledge is distilled from a complex…
In many real-world visual Imitation Learning (IL) scenarios, there is a misalignment between the agent's and the expert's perspectives, which might lead to the failure of imitation. Previous methods have generally solved this problem by…
We propose ClassroomKD, a novel multi-mentor knowledge distillation framework inspired by classroom environments to enhance knowledge transfer between the student and multiple mentors with different knowledge levels. Unlike traditional…
Pre-training a large transformer model on a massive amount of unlabeled data and fine-tuning it on labeled datasets for diverse downstream tasks has proven to be a successful strategy, for a variety of vision and natural language processing…
Vision-and-Language Navigation (VLN) requires an agent to find a specified spot in an unseen environment by following natural language instructions. Dominant methods based on supervised learning clone expert's behaviours and thus perform…
Pretrained language models have led to significant performance gains in many NLP tasks. However, the intensive computing resources to train such models remain an issue. Knowledge distillation alleviates this problem by learning a…
Knowledge distillation deals with the problem of training a smaller model (Student) from a high capacity source model (Teacher) so as to retain most of its performance. Existing approaches use either the training data or meta-data extracted…
Recent recommender systems have shown remarkable performance by using an ensemble of heterogeneous models. However, it is exceedingly costly because it requires resources and inference latency proportional to the number of models, which…
We present a novel framework of knowledge distillation that is capable of learning powerful and efficient student models from ensemble teacher networks. Our approach addresses the inherent model capacity issue between teacher and student…
In real teaching scenarios, an excellent teacher always teaches what he (or she) is good at but the student is not. This gives the student the best assistance in making up for his (or her) weaknesses and becoming a good one overall.…
Knowledge distillation is a popular technique for transferring the knowledge from a large teacher model to a smaller student model by mimicking. However, distillation by directly aligning the feature maps between teacher and student may…
Knowledge distillation aims to train a compact student network using soft supervision from a larger teacher network and hard supervision from ground truths. However, determining an optimal knowledge fusion ratio that balances these…
A popular approach to model compression is to train an inexpensive student model to mimic the class probabilities of a highly accurate but cumbersome teacher model. Surprisingly, this two-step knowledge distillation process often leads to…
Contrastive Learning and Masked Image Modelling have demonstrated exceptional performance on self-supervised representation learning, where Momentum Contrast (i.e., MoCo) and Masked AutoEncoder (i.e., MAE) are the state-of-the-art,…