Search Results for author:
Found 16 papers, 7 papers with code
Phi-3 Technical Report: A Highly Capable Language Model Locally on Your Phone
We introduce phi-3-mini, a 3. 8 billion parameter language model trained on 3. 3 trillion tokens, whose overall performance, as measured by both academic benchmarks and internal testing, rivals that of models such as Mixtral 8x7B and GPT-3. 5 (e. g., phi-3-mini achieves 69% on MMLU and 8. 38 on MT-bench), despite being small enough to be deployed on a phone.
SCHEME: Scalable Channel Mixer for Vision Transformers
The resulting $\textit{Scalable CHannEl MixEr}$ (SCHEME) can be plugged into any ViT architecture to obtain a gamut of models with different trade-offs between complexity and performance by controlling the block diagonal MLP structure.
Fully Authentic Visual Question Answering Dataset from Online Communities
Visual Question Answering (VQA) entails answering questions about images.
Dense Network Expansion for Class Incremental Learning
This is accomplished by the introduction of dense connections between the intermediate layers of the task expert networks, that enable the transfer of knowledge from old to new tasks via feature sharing and reusing.
Should All Proposals be Treated Equally in Object Detection?
We formulate this as a learning problem where the goal is to assign operators to proposals, in the detection head, so that the total computational cost is constrained and the precision is maximized.
MicroNet: Improving Image Recognition with Extremely Low FLOPs
This paper aims at addressing the problem of substantial performance degradation at extremely low computational cost (e. g. 5M FLOPs on ImageNet classification).
Dynamic Transfer for Multi-Source Domain Adaptation
However, such a static model is difficult to handle conflicts across multiple domains, and suffers from a performance degradation in both source domains and target domain.
Revisiting Dynamic Convolution via Matrix Decomposition
It has two limitations: (a) it increases the number of convolutional weights by K-times, and (b) the joint optimization of dynamic attention and static convolution kernels is challenging.
MicroNet: Towards Image Recognition with Extremely Low FLOPs
In this paper, we present MicroNet, which is an efficient convolutional neural network using extremely low computational cost (e. g. 6 MFLOPs on ImageNet classification).
Deep Hashing with Hash-Consistent Large Margin Proxy Embeddings
The use of a fixed set of proxies (weights of the CNN classification layer) is proposed to eliminate this ambiguity, and a procedure to design proxy sets that are nearly optimal for both classification and hashing is introduced.
Explainable Object-induced Action Decision for Autonomous Vehicles
The new paradigm lies between the end-to-end and pipelined approaches, and is inspired by how humans solve the problem.
Efficient Multi-Domain Network Learning by Covariance Normalization
The problem of multi-domain learning of deep networks is considered.
Efficient Multi-Domain Learning by Covariance Normalization
The problem of multi-domain learning of deep networks is considered.
Semantic Fisher Scores for Task Transfer: Using Objects to Classify Scenes
Somewhat surprisingly, the scene classification results are superior to those of a CNN explicitly trained for scene classification, using a large scene dataset (Places).
Bidirectional Learning for Domain Adaptation of Semantic Segmentation
In this paper, we propose a novel bidirectional learning framework for domain adaptation of segmentation.
Ranked #7 on
Semantic Segmentation
on DADA-seg
Deep Scene Image Classification With the MFAFVNet
This enables the design of a network architecture, the MFAFVNet, that can be trained in an end to end manner.
